Self-contained persona dispatch (no agents/ directory)

This skill is self-contained: its specialist personas live under references/personas/ and it depends on no registered subagent and no agents/ directory.

Whenever the steps below name a ce-* specialist — e.g. Task ce-<specialist>(args), "dispatch ce-<specialist>", or a persona-catalog entry:

1. Read references/personas/<name>.md.
2. If your harness can launch subagents (a Task/agent-dispatch tool or equivalent), launch one, passing that file's entire contents as the subagent's instructions, then append the specific args/context the step gives. When the persona's "Operating constraints" line says read-only, prefer a read-only/explore-type subagent if your harness offers one; otherwise use a general-purpose subagent.
3. If your harness cannot launch subagents, apply the persona inline: adopt the persona file as your own instructions for that step, complete it, then return to this skill's flow.
4. Honor the persona's "Operating constraints" line in either mode (tool/model limits are NOT otherwise enforced once de-plugin-ified). Dispatch independent personas in parallel when your harness supports it; personas never spawn further subagents.

Document Review

Review requirements or plan documents through multi-persona analysis. Dispatches specialized reviewer agents in parallel, auto-applies safe_auto fixes, and routes remaining findings through a four-option interaction (per-finding walk-through, auto-resolve with best judgment, Append-to-Open-Questions, Report-only) for user decision.

Interactive mode rules